{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T10:12:25Z","timestamp":1770977545831,"version":"3.50.1"},"reference-count":20,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T00:00:00Z","timestamp":1770940800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Competitive Research Fund of The University of Aizu, Japan"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Computers"],"abstract":"<jats:p>Autism Spectrum Disorder (ASD) is a neurological condition that affects communication and social interaction skills, with individuals experiencing a range of challenges that often require specialized care. Automated systems for recognizing ASD face significant challenges due to the complexity of identifying distinguishing features from facial images. This study proposes an incremental advancement in ASD recognition by introducing a dual-stream model that combines handcrafted facial-landmark features with deep learning-based pixel-level features. The model processes images through two distinct streams to capture complementary aspects of facial information. In the first stream, facial landmarks are extracted using MediaPipe (v0.10.21),with a focus on 137 symmetric landmarks. The face\u2019s position is adjusted using in-plane rotation based on eye-corner angles, and geometric features along with 52 blendshape features are processed through Dense layers. In the second stream, RGB image features are extracted using pre-trained CNNs (e.g., ResNet50V2, DenseNet121, InceptionV3) enhanced with Squeeze-and-Excitation (SE) blocks, followed by feature refinement through Global Average Pooling (GAP) and DenseNet layers. The outputs from both streams are fused using weighted concatenation through a softmax gate, followed by further feature refinement for classification. This hybrid approach significantly improves the ability to distinguish between ASD and non-ASD faces, demonstrating the benefits of combining geometric and pixel-based features. The model achieved an accuracy of 96.43% on the Kaggle dataset and 97.83% on the YTUIA dataset. Statistical hypothesis testing further confirms that the proposed approach provides a statistically meaningful advantage over strong baselines, particularly in terms of classification correctness and robustness across datasets. While these results are promising, they show incremental improvements over existing methods, and future work will focus on optimizing performance to exceed current benchmarks.<\/jats:p>","DOI":"10.3390\/computers15020124","type":"journal-article","created":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T09:09:19Z","timestamp":1770973759000},"page":"124","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["ASD Recognition Through Weighted Integration of Landmark-Based Handcrafted and Pixel-Based Deep Learning Features"],"prefix":"10.3390","volume":"15","author":[{"given":"Asahi","family":"Sekine","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, The University of Aizu, Aizuwakamatsu 965-8580, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1238-0464","authenticated-orcid":false,"given":"Abu Saleh Musa","family":"Miah","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, The University of Aizu, Aizuwakamatsu 965-8580, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Koki","family":"Hirooka","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, The University of Aizu, Aizuwakamatsu 965-8580, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-6499-1825","authenticated-orcid":false,"given":"Najmul","family":"Hassan","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, The University of Aizu, Aizuwakamatsu 965-8580, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Md. Al Mehedi","family":"Hasan","sequence":"additional","affiliation":[{"name":"Research Institute for Electronic Science (RIES), Hokkaido University, Sapporo 001-0020, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuichi","family":"Okuyama","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, The University of Aizu, Aizuwakamatsu 965-8580, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3509-6607","authenticated-orcid":false,"given":"Yoichi","family":"Tomioka","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, The University of Aizu, Aizuwakamatsu 965-8580, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7476-2468","authenticated-orcid":false,"given":"Jungpil","family":"Shin","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, The University of Aizu, Aizuwakamatsu 965-8580, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,2,13]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"103189","DOI":"10.1016\/j.scs.2021.103189","article-title":"Artificial intelligence and internet of things in screening and management of autism spectrum disorder","volume":"74","author":"Ghosh","year":"2021","journal-title":"Sustain. Cities Soc."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"104949","DOI":"10.1016\/j.compbiomed.2021.104949","article-title":"Deep learning for neuroimaging-based diagnosis and rehabilitation of autism spectrum disorder: A review","volume":"139","author":"Khodatars","year":"2021","journal-title":"Comput. Biol. Med."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"5791","DOI":"10.1007\/s00521-022-06960-9","article-title":"Literature review: Efficient deep neural networks techniques for medical image analysis","volume":"34","author":"Abdou","year":"2022","journal-title":"Neural Comput. Appl."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Wang, M., Xu, D., Zhang, L., and Jiang, H. (2023). Application of multimodal MRI in the early diagnosis of autism spectrum disorders: A review. Diagnostics, 13.","DOI":"10.3390\/diagnostics13193027"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Esqueda-Elizondo, J.J., Ju\u00e1rez-Ram\u00edrez, R., L\u00f3pez-Bonilla, O.R., Garc\u00eda-Guerrero, E.E., Galindo-Aldana, G.M., Jim\u00e9nez-Berist\u00e1in, L., Serrano-Trujillo, A., Tlelo-Cuautle, E., and Inzunza-Gonz\u00e1lez, E. (2022). Attention measurement of an autism spectrum disorder user using EEG signals: A case study. Math. Comput. Appl., 27.","DOI":"10.3390\/mca27020021"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"59","DOI":"10.37934\/araset.32.3.5974","article-title":"Effect of Different Modalities of Facial Images on ASD Diagnosis Using Deep Learning-Based Neural Network","volume":"32","author":"Alam","year":"2023","journal-title":"J. Adv. Res. Appl. Sci. Eng. Technol."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"C\u00eerneanu, A.L., Popescu, D., and Iordache, D. (2023). New trends in emotion recognition using image analysis by neural networks, a systematic review. Sensors, 23.","DOI":"10.3390\/s23167092"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Shin, J., Miah, A.S.M., Kakizaki, M., Hassan, N., and Tomioka, Y. (2025). Autism Spectrum Disorder Detection Using Skeleton-Based Body Movement Analysis via Dual-Stream Deep Learning. Electronics, 14.","DOI":"10.3390\/electronics14112231"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Derbali, M., Jarrah, M., and Randhawa, P. (2023). Autism Spectrum Disorder Detection: Video Games Based Facial Expression Diagnosis Using Deep Learning. Int. J. Adv. Comput. Sci. Appl., 14.","DOI":"10.14569\/IJACSA.2023.0140112"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"3713","DOI":"10.1007\/s11760-023-02598-9","article-title":"Control learning rate for autism facial detection via deep transfer learning","volume":"17","author":"Ikermane","year":"2023","journal-title":"Signal Image Video Process."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Shi, C., Xin, X., and Zhang, J. (2021). Domain adaptation using a three-way decision improves the identification of autism patients from multisite fMRI data. Brain Sci., 11.","DOI":"10.3390\/brainsci11050603"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Jung, S.K., Lim, H.K., Lee, S., Cho, Y., and Song, I.S. (2021). Deep active learning for automatic segmentation of maxillary sinus lesions using a convolutional neural network. Diagnostics, 11.","DOI":"10.3390\/diagnostics11040688"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"102168","DOI":"10.1016\/j.compmedimag.2022.102168","article-title":"Deep-active-learning approach towards accurate right ventricular segmentation using a two-level uncertainty estimation","volume":"104","author":"Ammari","year":"2023","journal-title":"Comput. Med. Imaging Graph."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Alam, M.S., Elsheikh, E.A., Suliman, F., Rashid, M.M., and Faizabadi, A.R. (2024). Innovative strategies for early autism diagnosis: Active learning and domain adaptation optimization. Diagnostics, 14.","DOI":"10.3390\/diagnostics14060629"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Alam, M.S., Rashid, M.M., Roy, R., Faizabadi, A.R., Gupta, K.D., and Ahsan, M.M. (2022). Empirical study of autism spectrum disorder diagnosis using facial images by improved transfer learning approach. Bioengineering, 9.","DOI":"10.3390\/bioengineering9110710"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Alam, M.S., Rashid, M.M., Jazlan, A., Alahi, M.E.E., Kchaou, M., and Alharthi, K.A.B. (2025). Robust Autism Spectrum Disorder Screening Based on Facial Images (For Disability Diagnosis): A Domain-Adaptive Deep Ensemble Approach. Diagnostics, 15.","DOI":"10.3390\/diagnostics15131601"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Alam, M.S., Rashid, M.M., Faizabadi, A.R., Mohd Zaki, H.F., Alam, T.E., Ali, M.S., Gupta, K.D., and Ahsan, M.M. (2023). Efficient deep learning-based data-centric approach for autism spectrum disorder diagnosis from facial images using explainable AI. Technologies, 11.","DOI":"10.3390\/technologies11050115"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"11","DOI":"10.32604\/iasc.2023.030125","article-title":"Early detection of autism in children using transfer learning","volume":"36","author":"Ghazal","year":"2023","journal-title":"Intell. Autom. Soft Comput."},{"key":"ref_19","first-page":"883","article-title":"Refurbished and improvised model using convolution network for autism disorder detection in facial images","volume":"29","author":"Kaur","year":"2023","journal-title":"Indones. J. Electr. Eng. Comput. Sci"},{"key":"ref_20","first-page":"1140","article-title":"Web-based autism screening using facial images and a convolutional neural network","volume":"29","author":"Ikermane","year":"2023","journal-title":"Indones. J. Electr. Eng. Comput. Sci"}],"container-title":["Computers"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-431X\/15\/2\/124\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T09:19:24Z","timestamp":1770974364000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-431X\/15\/2\/124"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,13]]},"references-count":20,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,2]]}},"alternative-id":["computers15020124"],"URL":"https:\/\/doi.org\/10.3390\/computers15020124","relation":{},"ISSN":["2073-431X"],"issn-type":[{"value":"2073-431X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,13]]}}}